Chapter 11: Hyperparameter Tuning and Automated Machine Learning
In the previous chapter, we learned how to train convolutional neural networks and complex deep neural networks. When training these models, we are often confronted with difficult choices in terms of the various parameters we should use, such as the number of layers, filter dimensions, the type and order of layers, regularization, batch size, learning rate, the number of epochs, and many more. And this is not only the case for DNNs – the same challenges arise when we need to select the correct preprocessing steps, features, models, and model parameters in statistical ML approaches.
In this chapter, we will look at optimizing the training process to remove some of the non-optimal ...
Get Mastering Azure Machine Learning - Second Edition now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
